18results about How to "Accurate score" patented technology

The invention discloses a large model capability assessment method and device and a storage medium, and relates to the technical field of artificial intelligence and deep learning, and the method comprises the steps: carrying out the reasoning operation of test data through a preset reasoning model, and obtaining model answer data, the test data does not contain a data set with label information; a target scoring mode matched with the data size of the model answer data is determined, the model answer data is scored according to the target scoring mode, an evaluation score is obtained, and the target scoring mode scores the model answer data through at least two ability dimensions; the evaluation score is output and forms score data with the test data. According to the invention, the accuracy of large model capability evaluation in the government affair circulation field can be improved.

The invention discloses a ship navigation path planning method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a target area of ship navigation, and rasterizing the target area to obtain navigable grids of a ship; constructing a transmission network of the ship in the target period; the transmission network takes navigable grids as nodes, takes a navigation path between two nodes as a directed edge, and takes the ship average flow of each navigation path in a target period as the weight of the directed edge; ship information and environment information in the target area are acquired in real time, and the weight of each directed edge in the transmission network is updated in real time based on the acquired ship information and environment information; based on the weight of each directed edge, determining a comprehensive score of each node in the transmission network; and determining a preset number of nodes with high comprehensive scores as target nodes, and determining a navigation path of the ship based on the target nodes. According to the invention, the optimal navigation path of the ship can be planned, and the navigation efficiency and safety are improved.

The invention discloses a method for evaluating the comprehensive quality of dried orange peel based on a near-infrared spectrometer and an analytic hierarchy process-entropy weight method, and belongs to the technical field of optical analysis, and the method comprises the following steps: preparing a dried orange peel sample, acquiring near-infrared spectrum data of the dried orange peel sample, and preprocessing; acquiring the year information of the production place of the dried orange peel sample, and measuring the hesperidin content, the nobiletin content, the tangeretin content, the anti-inflammatory activity, the delicate flavor, the sweet taste, the bitter taste, the overall preference degree and the comprehensive score value of the dried orange peel in the dried orange peel sample; establishing a pericarpium citri reticulatae producing area year discrimination model, a hesperidin quantitative model, a nobiletin quantitative model, a tangeretin quantitative model, an anti-inflammatory activity quantitative model, a delicate flavor quantitative model, a sweet taste quantitative model, a bitter taste quantitative model, an overall preference quantitative model and a comprehensive score quantitative model; and detecting a to-be-detected dried orange peel sample, and evaluating the dried orange peel quality. The method has the advantages of economy, simplicity, convenience, rapidness, greenness and the like, and provides a basis for comprehensively evaluating the quality of the pericarpium citri reticulatae.

The invention belongs to the technical field of computer natural languages, and discloses a training data screening method for a large language model in the government affair field, electronic equipment and a storage medium, and the training data screening method for the large language model in the government affair field comprises the following steps: obtaining an original data set based on the government affair field; training based on the original data set to obtain a scoring model; calling a scoring model to perform quality evaluation on the original data set to obtain a quality data set; obtaining a seed data set according to the quality data set; and obtaining a training data set according to the seed data set. According to the method, the scoring model is trained based on the original data set, so that the scoring model has better adaptability to the large voice model, and the scoring model is used for evaluating the quality of the instruction, so that the screened training data is more accurate.

The invention provides an improved deployment method and system for a multi-feature fusion entity co-reference resolution model. The method comprises the following steps: S1, constructing a multi-feature fusion entity co-reference resolution model; the multi-feature fusion entity co-reference resolution model comprises a word embedding layer, a feature extraction layer, a to-be-resolved item trimming layer and an output layer; and S2, processing an input text by using different layers of the multi-feature fusion entity co-reference resolution model, and deploying the multi-feature fusion entity co-reference resolution model. According to the end-to-end-based multi-feature fusion entity co-reference resolution model provided by the invention, by effectively capturing semantic information and contexts of words, potential co-reference relationships in documents are deeply mined, and a machine is helped to more efficiently and accurately understand and analyze complex texts.

The invention discloses a commodity scoring method and device and a related product. The method comprises the steps of obtaining feedback data of an object on a target commodity and a plurality of target commodity orders associated with the feedback data; based on the feedback data and a plurality of target commodity orders associated with the feedback data, obtaining an experience type and an emotion type of each target commodity order; the experience type of each target commodity order is used for indicating the experience feedback of the object on the target commodity in the target dimension, and the emotion type of each target commodity order is used for indicating the satisfaction degree of the object on the target commodity; and generating a score of the target commodity based on the experience types corresponding to the plurality of target commodity orders and the emotion types corresponding to the plurality of target commodity orders. Therefore, based on the analysis of the feedback text, the score is generated by comprehensively considering the experience feedback of the user on the target commodity in different dimensions and the satisfaction degree of the user on the target commodity, the relevance between the score and the feedback text is enhanced, and the scoring accuracy can be improved.

The utility model relates to the technical field of scoring systems for target vehicles, and particularly discloses a scoring system for a target vehicle, which comprises a shooting target body and a plurality of annular rings arranged on the shooting target body, and is characterized in that each annular ring consists of a plurality of elastic plates, and main pressure sensors are arranged at the bottoms of the elastic plates; the device further comprises a precision scoring system, the precision scoring system comprises a control chip, a controller, a light-emitting module, a light-emitting lamp set, a large counting module and a storage module, the number of the main pressure sensors is equal to that of the elastic plates, and the main pressure sensors are electrically connected with the controller. The device solves the problem that a traditional shooting target scoring system is not accurate in scoring.

The present invention relates to data processing, and discloses a user classification method, including: establishing hierarchical labels for each data set based on the description information of the data set, establishing a label tree based on the hierarchical labels, and taking the set of data sets corresponding to the same leaf node label in the label tree as a data set group; determining the target leaf node label based on the data set requirement text, taking the data set group corresponding to the target leaf node label as the target data set group, and calculating the comprehensive score of each data set in the target data set group based on historical modeling data; sorting the data sets in the target data set group based on the comprehensive score, determining the target data set based on the sorting result, and performing joint modeling based on the target data set to obtain a target user classification model; inputting user data into the target user classification model to obtain a user classification result. The present invention also provides a user classification device, an electronic device, and a readable storage medium. The present invention improves the accuracy of user classification.

The invention relates to the technical field of computer vision, in particular to a multi-person shadowboxing motion image recognition scoring method and a storage medium. The scoring method comprises the following steps: synchronously shooting N paths of global images of multi-person shadowboxing movement in a target area from N different angles, and tracking three-dimensional coordinates of UWB tags worn by participants at shooting moments by using a UWB positioning technology; cutting out N paths of local images corresponding to each participant from the N paths of global images according to the three-dimensional coordinates of the UWB tag worn by each participant at each shooting moment; and detecting human body key point coordinates of the participant in each local image by using a pre-trained key point detection model, further generating N key point coordinate time sequences of the participant, respectively inputting the N key point coordinate time sequences into N pre-trained scoring models, obtaining N scores of the participant, and averaging the N scores to obtain a final score of the participant. According to the method, the scoring problem in multi-person shadowboxing sports is solved.

This invention discloses a method, storage medium, and device for batch re-grading of test questions. By extracting and reusing the standard question stem from a single assignment, it avoids repeatedly identifying the question stem for each assignment, significantly improving processing efficiency. By cropping and stitching together the clean answer traces of all students to form an aggregated image, it achieves a highly efficient "one-time input, batch grading" mode. Combined with a multimodal grading model, it can simultaneously understand the question requirements and each student's handwritten answer, accurately score, and generate feedback. With the addition of a caching mechanism and dynamic batching strategy, it can also adapt to different scales of re-grading needs, saving computing resources. This invention can significantly reduce the burden on teachers overall, improve the consistency and intelligence of grading, and is particularly suitable for teaching scenarios such as exam review and unified grading.

Embodiments of this application disclose a scoring method and a related apparatus, to score reply content of a user, so as to accurately assess an employee. The method in embodiments of this application includes: obtaining reply content of a user to a target question; extracting M groups of candidate assessment points from the reply content based on M target assessment points, where the M target assessment points are obtained based on a target answer to the target question, each group of candidate assessment points includes N candidate assessment points and corresponds to one target assessment point, each candidate assessment point includes a plurality of consecutive characters in the reply content, and both M and N are positive integers; and obtaining a score of the reply content based on the M groups of candidate assessment points and the M target assessment points.

The application provides a user security level determination method and device based on user service change, which comprises the following steps: inputting user feature data of candidate users in a candidate user group into a trained user screening model to obtain a first user score for representing change probability of specific business service of the user; determining a specific user in the candidate user group according to the first user score; determining a second user score according to the first user score and the user feature data of the specific user; and determining a security level of the specific user based on the first user score and the second user score. The application determines possible change conditions of services that the user can enjoy from the condition that the user enjoys changed services, effectively quantifies change condition information of the user's demand for internet services from the dimension of change condition information of the specific business service from nothing to something, and can accurately determine the security level of the specific user and change condition information thereof.

The disclosed embodiments disclose an object evaluation processing method and device, as well as a merchant evaluation presentation method and device. The object evaluation processing method not only considers the user's rating of the object, but also considers the user's evaluation of the object and the object's feedback on the user's evaluation, thereby expanding the dimension of object evaluation, expanding the evaluation distinction between objects, and improving the impact of the rating and evaluation on the object as a whole. The processing of the rating and evaluation by the user and the object will affect the overall rating and the evaluation of the corresponding dimensions. Therefore, the rating and evaluation of the object are more accurate, which is conducive to improving the rating and evaluation of the object, and is also conducive to the user identifying the rating and evaluation of each dimension of the object.

The present invention relates to a method and system for automatic scoring of subjective questions based on knowledge graphs. Firstly, a triple extraction component is used to extract knowledge triples from student answers and standard answers to subjective questions respectively, and then the knowledge triples matched in the student answers are input into a trained knowledge graph embedding model, and the similarity score of each successfully matched triple is output. Finally, the score of each scoring point in the triple score sequence is determined according to the scoring rule to obtain the total score of the student answers to the subjective questions. The trained knowledge graph embedding model is trained according to the knowledge graph library of the student's professional field, rather than using a general public knowledge graph, so that the system is more accurate in professional detection and scoring, thereby realizing accurate automatic scoring of subjective questions.

The present application provides an audio answer scoring method, apparatus, device, storage medium and product, the method comprising: obtaining a target answer audio and a first task instruction, the first task instruction comprising description information of the scoring task, question information corresponding to the target answer audio and a scoring rule; inputting the target answer audio and the first task instruction into a pre-trained multimodal large language model, the multimodal large language model outputting a scoring result for the target answer audio; the multimodal large language model is obtained by executing a first training task and a second training task, the first training task being used to score the first sample answer audio based on a transcribed text of the first sample answer audio, the second training task being used to determine a score for the first sample answer audio by processing the first sample answer audio, the scoring result of the first training task being used as a scoring label for the second training task.

Embodiments of the present application provide a model training and content display method and device, equipment and medium, relating to the technical field of artificial intelligence. The method comprises: obtaining a training sample set, the training sample set comprising a plurality of original content samples carrying labels, the plurality of original content samples being generated from target data, the number of clicks of the target data being less than a preset threshold, and the label representing the click probability of the target data; adding perturbation information to the plurality of original content samples to obtain a plurality of adversarial content samples; inputting the plurality of original content samples and the plurality of adversarial content samples into a click rate estimation model respectively to obtain a plurality of first gradients corresponding to the plurality of original content samples and a plurality of second gradients corresponding to the plurality of adversarial content samples; and adjusting parameters of the click rate estimation model according to the plurality of first gradients and the plurality of second gradients. The technical solution provided by the embodiments of the present application can improve the content recommendation effect and improve the search efficiency of users.

The invention provides a cosmetic cleaning effect visual evaluation method and application thereof, and the method comprises the steps: S1, providing a cosmetic cleaning effect visual evaluation score table which comprises a referable map corresponding to each grade of score; s2, uniformly coating a preset amount of to-be-cleaned substance on a human skin test area to simulate dirt on the surface of the human skin; s3, scoring the human skin test area, and recording the score as T1; s4, fully cleaning a human skin test area by using a test cosmetic; s5, scoring the human skin test area, and recording the score as T2; and S6, calculating the score change rate of the visual evaluation score, wherein the calculation formula of the score change rate delta is delta = [(T2-T1) / T1] * 100%. According to the method, the cleaning effect of the cosmetics can be evaluated more objectively and consistently, and subjectivity and errors in the evaluation process can be reduced.

The application belongs to the technical field of artificial intelligence, and discloses a team cooperation optimization method, device, equipment and storage medium, the team cooperation optimization method comprises the following steps: inputting human time sequence characteristics in team interaction video into a time sequence behavior analysis and evaluation model to output a score of a preset team cooperation index corresponding to the team interaction video; analyzing an emotional index of a target team for the team cooperation index according to key cooperation data related to the team cooperation index; adjusting the score of the team cooperation index according to the emotional index; and generating a cooperation optimization strategy for optimizing the score of the team cooperation index. The application can be applied to financial technology, medical health and other business management systems, solves the problems of human bias in the evaluation process and the inability to evaluate in real time in the prior art, and solves the technical problem that optimization of team cooperation based on evaluation results cannot truly achieve optimization.